Odysseus: Scaling VLMs to 100+ Turn Decision-Making in Games via Reinforcement Learning
Paper • 2605.00347 • Published • 13
Xinran Liang
xinranliang
AI & ML interests
None yet
Recent Activity
upvoted a paper about 1 year ago
COMPACT: COMPositional Atomic-to-Complex Visual Capability Tuning upvoted a paper over 1 year ago
Unifying Specialized Visual Encoders for Video Language ModelsOrganizations
None yet